A Shared ChatGPT Link Could Run Attacker Code in a User's Session and Read Private Chats

Researchers at the security firm Parameter showed that a malicious shared ChatGPT link could run attacker code in the logged-in session of anyone who opened it and read their private conversations. OpenAI fixed the flaw eight days after it was reported and rated it P1, its most serious category. Parameter did not report real-world use of the flaw; the work was a controlled test.